Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     permeated
    0.64
     thrived
    0.57
     plummeted
    0.57
     galore
    0.52
     jsou
    0.52
     gripped
    0.51
     betroffen
    0.51
     υπάρχει
    0.51
     thrives
    0.50
     thriving
    0.50
    POSITIVE LOGITS
    把
    0.76
    将
    0.68
    将其
    0.66
    尝试
    0.64
     attempt
    0.63
    assign
    0.61
    添加
    0.61
     apply
    0.59
    用
    0.59
    將
    0.59
    Act Density 0.043%

    No Known Activations